how to label features extracted from image using extractFeatures() and divide them in testing and training sets?
6 views (last 30 days)
Show older comments
if I use detectSURFFeatures() Then extractFeatures() for 47 images Then I need to split those features extracted from 47 images into training n testing sets also label them +1/-1 for svm how can I do it using matlab.
2 Comments
Answers (2)
Image Analyst
on 24 Oct 2015
If you have the Statistics and Machine Learning toolbox, you can use randsample()
0 Comments
KJVKU999
on 29 Oct 2015
How many surf point you are using? Are you using all available points? You can use Classification Learner application available with statistics and machine learning toolbox.
Save your features in table format and load that table from the application. While making it in table format, also include one column named 'Label' wherein you can give class name or number.
Toolbox will take care of the training and testing once you specify validation method.
0 Comments
See Also
Categories
Find more on Deep Learning for Image Processing in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!